Does feature selection improve classification accuracy? Impact of sample size and feature selection on classification using anatomical magnetic resonance images

Topic: Brain imaging, connectivity and assessment

There are growing numbers of studies using machine learning approaches to characterize patterns of anatomical difference discernible from neuroimaging data. The high-dimensionality of image data often raises a concern that feature selection is needed to obtain optimal accuracy. Among previous studies, mostly using fixed sample sizes, some show greater predictive accuracies with feature selection, whereas others do not. In this study, we compared four common feature selection methods. 1) Pre-selected region of interests (ROIs) that are based on prior knowledge. 2) Univariate t-test filtering. 3) Recursive feature elimination (RFE), and 4) t-test filtering constrained by ROIs. The predictive accuracies achieved from different sample sizes, with and without feature selection, were compared statistically. To demonstrate the effect, we used grey matter segmented from the T1-weighted anatomical scans collected by the Alzheimer's disease Neuroimaging Initiative (ADNI) as the input features to a linear support vector machine classifier. The objective was to characterize the patterns of difference between Alzheimer's disease (AD) patients and cognitively normal subjects, and also to characterize the difference between mild cognitive impairment (MCI) patients and normal subjects. In addition, we also compared the classification accuracies between MCI patients who converted to AD and MCI patients who did not convert within the period of 12 months. Predictive accuracies from two data-driven feature selection methods (t-test filtering and RFE) were no better than those achieved using whole brain data. We showed that we could achieve the most accurate characterizations by using prior knowledge of where to expect neurodegeneration (hippocampus and parahippocampal gyrus). Therefore, feature selection does improve the classification accuracies, but it depends on the method adopted. In general, larger sample sizes yielded higher accuracies with less advantage obtained by using knowledge from the existing literature.

Key findings

• We showed that we could achieve the most accurate characterizations by using prior knowledge of where to expect neurodegeneration (hippocampus and parahippocampal gyrus).

New to this subject? Start with our plain-English guide: Digital health →

Study details

• Evidence strengthLow

Read the original

• DOI: 10.1016/j.neuroimage.2011.11.066
• PubMed: 22166797
• Original source →

Free copy unknown: no free-copy check has an answer for this record yet. That does not mean it is paywalled.

@article{chu2012-22166797,
  author  = {Chu, C. and Hsu, A. L. and Chou, K. H. and Bandettini, P. and Lin, C. and {Alzheimer's Disease Neuroimaging Initiative}},
  title   = {{Does feature selection improve classification accuracy? Impact of sample size and feature selection on classification using anatomical magnetic resonance images}},
  journal = {NeuroImage},
  year    = {2012},
  doi     = {10.1016/j.neuroimage.2011.11.066},
  pmid    = {22166797},
  url     = {https://doi.org/10.1016/j.neuroimage.2011.11.066}
}

Related studies in Digital health tools

• Comparison of Feature Selection Techniques in Machine Learning for Anatomical Brain MRI in Dementia Neuroinformatics · 2016-07-01 · usefulness score 38/100
• Machine learning on subcortical brain features: A study of sample size efficiency for neurodegenerative disease classification bioRxiv · 2026-09-21 · usefulness score 16/100
• Predicting Prodromal Alzheimer's Disease in Subjects with Mild Cognitive Impairment Using Machine Learning Classification of Multimodal Multicenter Diffusion-Tensor and Magnetic Resonance Imaging Data Journal of neuroimaging : official journal of the American Society of Neuroimaging · 2015-01-28 · usefulness score 40/100
• Enhanced in silico QSAR-based screening of butyrylcholinesterase inhibitors using multi-feature selection and machine learning SAR and QSAR in environmental research · 2025-02-01 · usefulness score 34/100
• Early Detection of Alzheimer's Disease Using Magnetic Resonance Imaging: A Novel Approach Combining Convolutional Neural Networks and Ensemble Learning Frontiers in neuroscience · 2020-05-13 · usefulness score 41/100
• Classification of Alzheimer's Disease by Combination of Convolutional and Recurrent Neural Networks Using FDG-PET Images Frontiers in neuroinformatics · 2018-06-19 · usefulness score 53/100

Similar studies

• Multivariate data analysis and machine learning in Alzheimer's disease with a focus on structural magnetic resonance imaging 2014 · Digital health tools
• Machine learning framework for early MRI-based Alzheimer's conversion prediction in MCI subjects 2015 · Digital health tools
• Automatic classification of patients with Alzheimer's disease from structural MRI: a comparison of ten methods using the ADNI database 2011 · Brain scans and imaging
• Boosting power for clinical trials using classifiers based on multiple biomarkers 2010 · Digital health tools
• Predicting conversion from MCI to AD using resting-state fMRI, graph theoretical approach and SVM 2017 · Digital health tools
• Gaussian process classification of Alzheimer's disease and mild cognitive impairment from resting-state fMRI 2015 · Digital health tools

More on Digital health tools

• A review that covers this ground Transfer Learning in Magnetic Resonance Brain Imaging: A Systematic Review Journal of imaging · 2021-04-01 · usefulness score 42/100
• Newest in this subject Speaker-Wise Dementia Screening fromNaturalistic Speech with Lexical Entropy, Semantic Drift, and Multimodal Fusion Research Square · 2026-10-21 · Preprint — not yet peer-reviewed · usefulness score 16/100
• Newest in this subject Integrating Multisource Target Evidence with Machine-Learning Potency Prediction for Alzheimer’s Disease Drug Discovery bioRxiv · 2026-10-20 · Preprint — not yet peer-reviewed · usefulness score 16/100

See all studies in Digital health tools →